Augmented Reality enhances the user perception by overlaying real world information with computer-generated information. In this paper, we study the user experience in Augmented Reality for the deployment of real-time adaptation. In the context of thin-client mobile Augmented Reality, the rate is often constrained due to limitations in the transmission link. End-to-end delay, frame rate, image size and head motion speed have been identified as important variables impacting the user experience. We propose a model to link the effect of these variables with the Quality of Experience metrics. Using this model, we present an adaptation scheme that adapts, in real time, the frame rate and the image size to maximize the Quality of Experience according to the context while satisfying the given rate constraint. Simulation shows the efficiency of the proposed scheme which achieves a better Quality of Experience than without adaptation. The adaptation still performs better than a solution with a fixed frame rate set to its maximum value.